sd-neo-mcp

sd-neo-mcp

MCP server and CLI tool connecting to SD WebUI Forge NEO, enabling image generation, model management, and more via natural language.

Category
Visit Server

README

sd-neo-mcp

SD WebUI Forge NEO 的 MCP 服务器与 CLI 工具。同时作为 opencode 的 stdio MCP 服务器与命令行工具 sdneo，连接运行中的 SD WebUI Forge NEO 实例（基于 A1111 的 /sdapi/v1/* HTTP API）。

功能

8 个 MCP 工具

工具 说明
generate_image 文生图，支持异步队列（agent-scheduler 扩展）或同步模式
image_to_image 图生图，基于输入图片和提示词生成新图片
list_models 列出可用 checkpoint 模型，标记当前活跃模型
switch_model 切换当前 checkpoint 模型
list_loras 列出可用 LoRA 模型
get_progress 查询生成进度（同步进度或异步任务状态）
upscale_images 放大图片（倍率/指定尺寸模式）
interrogate_image 图片反推标签（需 wd14-tagger 扩展）

CLI 子命令

sdneo status / gen / img2img / models / loras / progress / upscale / tag，每个子命令调用对应的 core dispatch 逻辑。

双传输模式

  • async：自动探测 agent-scheduler 扩展，入队后轮询直到完成
  • sync：回退到同步 /sdapi/v1/txt2img（单次阻塞）

前置条件

  • SD WebUI Forge NEO 必须以 --api 启动
  • 异步队列需启用 sd-webui-agent-scheduler-neo 扩展（可选，无则自动回退同步模式）
  • 图片反推需启用 sd-webui-wd14-tagger 扩展（可选）
  • Node.js >= 18.17

安装

cd sd-neo-mcp
npm install
npm run build

opencode 接入

在 opencode.json 的 mcp 块中添加（参考 opencode.example.json）：

{
  "mcp": {
    "sd-neo": {
      "type": "local",
      "command": ["node", "E:/download/sd-neo-mcp/dist/mcp/server.js"],
      "environment": {
        "SD_WEBUI_URL": "http://127.0.0.1:7860",
        "SD_OUTPUT_DIR": "E:/download/sd-neo-mcp/output"
      }
    }
  }
}

若 NEO 启用了 --api-auth，在 environment 中加 SD_AUTH_USER 和 SD_AUTH_PASS（不要设空串，留空即不启用）。

重启 opencode 生效。

环境变量

变量 默认值 说明
SD_WEBUI_URL http://127.0.0.1:7860 SD WebUI API 地址
SD_AUTH_USER - HTTP Basic Auth 用户名（需与 SD_AUTH_PASS 同时设置）
SD_AUTH_PASS - HTTP Basic Auth 密码
SD_OUTPUT_DIR ./output 图片输出目录（自动创建）
SD_GEN_TIMEOUT 600000 生成超时（毫秒）
SD_ASYNC_POLL_INTERVAL 1500 异步轮询间隔（毫秒）
SD_REQUEST_TIMEOUT 300000 HTTP 请求超时（毫秒）
SD_DEFAULT_SAMPLER - 默认采样器
SD_DEFAULT_STEPS - 默认步数
SD_DEFAULT_CFG - 默认 CFG 值

构建验证

npm run typecheck
npm run build
npm test
node dist/cli/index.js --help

项目结构

src/
  core/           # 核心业务层，不依赖 MCP/CLI
    config.ts     # 环境变量解析
    client.ts     # NEO API 客户端
    transport.ts  # async/sync 传输层
    tools.ts      # 8 个工具 dispatch
    schema.ts     # zod 输入 schema → JSON Schema
  mcp/
    server.ts     # MCP stdio 服务器
  cli/
    index.ts      # CLI 入口
tests/            # vitest 单元测试

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured